主流图像生成模型过度追求美观，压制了用户表达反美学艺术意图的自由。
Position: Universal Aesthetic Alignment Narrows Artistic Expression
- 构建多维度美学数据集，测试生成与评分模型对反审美指令的响应。
- 模型常将负面或低质提示误生成为美观图像，评分模型也惩罚符合提示的反美学作品。
- 适合关注AI艺术创作自由、审美偏见与用户自主权的研究者与创作者。
将图像生成模型过度对齐于通用审美偏好，会违背用户意图，尤其在要求生成‘反美学’作品用于艺术或批判性表达时。这种倾向优先体现开发者价值观，损害用户自主性与审美多样性。本文通过构建涵盖广泛美学范围的数据集，评估前沿生成与奖励模型的表现。结果显示，美学对齐的生成模型频繁默认输出符合传统审美的图像，无法遵循低质量或负面图像的指令；关键的是，奖励模型即使在图像完全匹配用户明确提示的情况下，仍会惩罚反美学内容。我们通过图像编辑与真实抽象艺术对比验证了这一系统性偏差。代码、微调模型及数据集已公开于：https://weathon.github.io/icml2026_position/。
原文摘要 · Abstract (English)
Over-aligning image generation models to a generalized aesthetic preference conflicts with user intent, particularly when "anti-aesthetic" outputs are requested for artistic or critical purposes. This adherence prioritizes developer-centered values, compromising user autonomy and aesthetic pluralism. We test this bias by constructing a wide-spectrum aesthetics dataset and evaluating state-of-the-art generation and reward models. This position paper finds that aesthetic-aligned generation models frequently default to conventionally beautiful outputs, failing to respect instructions for low-quality or negative imagery. Crucially, reward models penalize anti-aesthetic images even when they perfectly match the explicit user prompt. We confirm this systemic bias through image-to-image editing and evaluation against real abstract artworks. Our code, fine-tuned models, and datasets are available on our meta-expression intentionally anti-aesthetics webpage: https://weathon.github.io/icml2026_position/.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。